Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

docs(build): fix typo #352

Merged
merged 6 commits into from
Apr 14, 2022
Merged

docs(build): fix typo #352

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
7f198ff
docs(build): add missing build option
tpoisonooo Apr 13, 2022
a9e816e
docs(build): add onnx install
tpoisonooo Apr 14, 2022
f063e14
style(doc): trim whitespace
tpoisonooo Apr 14, 2022
3574dbf
docs(build): revert install onnx
tpoisonooo Apr 14, 2022
c3014b7
docs(build): add ncnn LD_LIBRARY_PATH
tpoisonooo Apr 14, 2022
3c82cef
docs(build): fix path error
tpoisonooo Apr 14, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 11 additions & 1 deletion docs/en/build/linux.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,6 +84,14 @@ conda install pytorch==1.8.0 torchvision==0.9.0 cudatoolkit=11.1 -c pytorch -c c
export cu_version=cu111 # cuda 11.1
export torch_version=torch1.8
pip install mmcv-full==1.4.0 -f https://download.openmmlab.com/mmcv/dist/${cu_version}/${torch_version}/index.html
</code></pre>
</td>
</tr>
<tr>
<td>onnx </td>
<td>Install onnx as follows. Refer to the <a href="https://github.com/onnx/onnx">guide</a> for details.
<pre><code>
conda install -c conda-forge onnx
tpoisonooo marked this conversation as resolved.
Show resolved Hide resolved
</code></pre>
</td>
</tr>
Expand Down Expand Up @@ -445,9 +453,11 @@ You can also activate other engines after the model.

#### Build Demo

Take ncnn backend as example:

```Bash
cd ${MMDEPLOY_DIR}/build/install/example
mkdir -p build && cd build
cmake .. -DMMDeploy_DIR=${MMDEPLOY_DIR}/build/install/lib/cmake/MMDeploy
cmake .. -DMMDeploy_DIR=${MMDEPLOY_DIR}/build/install/lib/cmake/MMDeploy -Dncnn_DIR=${NCNN_DIR}/build/install/lib/cmake/ncnn
make -j$(nproc)
```
8 changes: 8 additions & 0 deletions docs/zh_cn/build/linux.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,14 @@ conda install pytorch==1.8.0 torchvision==0.9.0 cudatoolkit=11.1 -c pytorch -c c
export cu_version=cu111 # cuda 11.1
export torch_version=torch1.8
pip install mmcv-full==1.4.0 -f https://download.openmmlab.com/mmcv/dist/${cu_version}/${torch_version}/index.html
</code></pre>
</td>
</tr>
<tr>
<td>onnx </td>
<td>参考如下命令安装 onnx。更多安装方式，可查看 <a href="https://github.com/onnx/onnx">onnx 官网</a><br>
<pre><code>
conda install -c conda-forge onnx
</code></pre>
</td>
</tr>
Expand Down
4 changes: 2 additions & 2 deletions mmdeploy/core/rewriters/rewriter_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,7 +181,7 @@ def check(self, env: Dict) -> bool:


class RewriterRegistry:
"""A registry that recoreds rewrite objects.
"""A registry that records rewrite objects.

Logically this class is a two-dimensional table which maintains an object
list for each backend. The records can be inserted to this table through
Expand Down Expand Up @@ -304,7 +304,7 @@ def register_object(self,
name (str): The import path to access the function/module.
backend (str): The rewriter will be activated on which backend.
ir (IR): The rewriter will be activated on which ir.
extra_chekcers (None | Checker | List[Checker]): Other requirements
extra_checkers (None | Checker | List[Checker]): Other requirements
for the rewriters. Default to `None`.

Returns:
Expand Down